A deep learning approach for mental health quality prediction using functional network connectivity and assessment data

Meenu Ajith; Dawn M Aycock; Erin B Tone; Jingyu Liu; Maria B Misiura; Rebecca Ellis; Sergey M Plis; Tricia Z King; Vonetta M Dotson; Vince Calhoun

doi:10.1007/s11682-024-00857-y

A deep learning approach for mental health quality prediction using functional network connectivity and assessment data

Brain Imaging Behav. 2024 Feb 10. doi: 10.1007/s11682-024-00857-y. Online ahead of print.

Authors

Meenu Ajith¹, Dawn M Aycock², Erin B Tone³, Jingyu Liu^{4

5}, Maria B Misiura^{3

6}, Rebecca Ellis⁷, Sergey M Plis⁸, Tricia Z King^{3

5}, Vonetta M Dotson^{9

10}, Vince Calhoun⁸

Affiliations

¹ Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, 55 Park Pl NE, Atlanta, GA, 30303, USA. majith@gsu.edu.
² Byrdine F. Lewis College of Nursing and Health Professions, Georgia State University, P.O. Box 4019, Atlanta, GA, 30302, USA.
³ Department of Psychology, Georgia State University, Atlanta, GA, USA.
⁴ Department of Computer Science, Georgia State University, Atlanta, GA, USA.
⁵ Neuroscience Institute, Georgia State University, Atlanta, GA, USA.
⁶ Departments of Neurology, Emory University, 615 Michael Street, Suite 505, Atlanta, GA, 30322, USA.
⁷ Department of Kinesiology and Health, Georgia State University, Atlanta, GA, USA.
⁸ Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, 55 Park Pl NE, Atlanta, GA, 30303, USA.
⁹ Department of Psychology, Georgia State University, P.O. Box 5010, Atlanta, GA, 30302-5010, USA.
¹⁰ Gerontology Institute, Georgia State University, Atlanta, GA, USA.

PMID: 38340285
DOI: 10.1007/s11682-024-00857-y

Abstract

While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model's performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.

Keywords: Assessment data; Deep learning; Mental health; rs-fMRI.

Grants and funding

2112455/Georgia State University RISE program and NSF grant